tuanna08go commited on
Commit
4824a2e
·
verified ·
1 Parent(s): 74765ef

Training in progress, step 26, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d7406848ad42852582b907bfed395182486b6c5e57b8c33566677485541ba35f
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c8d09284505a9d06766acc39b195c64e935de4cf65384350934da2380c8ba69
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:906e255e01d251325c76e63dd01c442fa61802e29320853a1ed11850c8b40f6c
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:379a3e58f68366de5618893c9240a44b96d894d86dc876bba0e7c1735705dcce
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15160272ffddfe27c654df211d1192733c9457f0ce97b19578f9cd078fb647f8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:638f0e887c7eab30601fcd15f109e577ce9025b567cf9228ffde08282c0e880e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e65bdb10468d12c8b6afa89fe8730e38a94a4f704431de04b0c1bf27440afce
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.010641019082212105,
5
  "eval_steps": 10,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -30,6 +30,21 @@
30
  "eval_samples_per_second": 169.265,
31
  "eval_steps_per_second": 21.163,
32
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  }
34
  ],
35
  "logging_steps": 10,
@@ -49,7 +64,7 @@
49
  "attributes": {}
50
  }
51
  },
52
- "total_flos": 47264563200.0,
53
  "train_batch_size": 8,
54
  "trial_name": null,
55
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.02128203816442421,
5
  "eval_steps": 10,
6
+ "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
30
  "eval_samples_per_second": 169.265,
31
  "eval_steps_per_second": 21.163,
32
  "step": 10
33
+ },
34
+ {
35
+ "epoch": 0.016370798588018622,
36
+ "grad_norm": 0.016160357743501663,
37
+ "learning_rate": 6.91341716182545e-05,
38
+ "loss": 11.9308,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 0.016370798588018622,
43
+ "eval_loss": 11.93083667755127,
44
+ "eval_runtime": 48.6409,
45
+ "eval_samples_per_second": 169.199,
46
+ "eval_steps_per_second": 21.155,
47
+ "step": 20
48
  }
49
  ],
50
  "logging_steps": 10,
 
64
  "attributes": {}
65
  }
66
  },
67
+ "total_flos": 94056480768.0,
68
  "train_batch_size": 8,
69
  "trial_name": null,
70
  "trial_params": null